Single-Cell Analyses of Colon and Blood Reveal Distinct Immune Cell Signatures of Ulcerative Colitis and Crohn's Disease

Abstract

Background & aims: Studies are needed to determine the mechanisms of mucosal dysregulation in patients with inflammatory bowel diseases (IBDs) and differences in inflammatory responses of patients with ulcerative colitis (UC) vs Crohn's disease (CD). We used mass cytometry (CyTOF) to characterize and compare immune cell populations in the mucosa and blood from patients with IBD and without IBD (controls) at single-cell resolution.

Methods: We performed CyTOF analysis of colonic mucosa samples (n = 87) and peripheral blood mononuclear cells (n = 85) from patients with active or inactive UC or CD and controls. We also performed single-cell RNA sequencing, flow cytometry, and RNA in situ hybridization analyses to validate key findings. We used random forest modeling to identify differences in signatures across subject groups.

Results: Compared with controls, colonic mucosa samples from patients with IBD had increased abundances of HLA-DR+CD38+ T cells, including T-regulatory cells that produce inflammatory cytokines; CXCR3+ plasmablasts; and IL1B+ macrophages and monocytes. Colonic mucosa samples from patients with UC were characterized by expansion of IL17A+ CD161+ effector memory T cells and IL17A+ T-regulatory cells; expansion of HLA-DR+CD56+ granulocytes; and reductions in type 3 innate lymphoid cells. Mucosal samples from patients with active CD were characterized by IL1B+HLA-DR+CD38+ T cells, IL1B+TNF+IFNG⁺ naïve B cells, IL1B+ dendritic cells (DCs), and IL1B+ plasmacytoid DCs. Peripheral blood mononuclear cells from patients with active CD differed from those of active UC in that the peripheral blood mononuclear cells from patients with CD had increased IL1B+ T-regulatory cells, IL1B+ DCs and IL1B+ plasmacytoid DCs, IL1B+ monocytes, and fewer group 1 innate lymphoid cells. Random forest modeling differentiated active UC from active CD in colonic mucosa and blood samples; top discriminating features included many of the cellular populations identified above.

Conclusions: We used single-cell technologies to identify immune cell populations specific to mucosa and blood samples from patients with active or inactive CD and UC and controls. This information might be used to develop therapies that target specific cell populations in patients with different types of IBD.

Keywords: ILC3; MAIT Cells; Treg; scRNA-Seq.

Figure 1.. T Cell Analysis Demonstrates UC- and CD-Specific Cytokine Signatures

A. Schematic of sample analysis methodology. B. Gating strategy to define T cells (CD3⁺CD45⁺) which were exported and subjected to dimensionality reduction (t-SNE) and clustering (FlowSOM) as depicted in labeled t-SNE cluster plot (right). C. CyTOF marker heatmap (rows are clusters, columns are markers, tile colors represent mean metal intensity per Color Key and Histogram legend scaled across all tiles). On the right are manually-labeled cluster identities and a schematic of cluster abundance in mucosa vs. periphery. Hierarchical clustering dendrogram on left of heatmap, with nodes numbered and selected nodes highlighted. Selected node branches outlined on heatmap and labeled on right. T cell memory subsets were assigned and color-coded (naïve: CD45RA⁺CD45RO⁻CCR7⁺CD27⁺; central memory [CM]: CD45RA⁻CD45RO⁺CCR7⁺CD27⁺; effector memory [EM]: CD45RA⁻CD45RO⁺CCR7⁻CD27^+/−; terminally differentiated effector memory cells re-expressing CD45RA [TEMRA]: CD45RA⁺CD45RO^+/−CCR7⁻CD27^+/−; and a subtype external to these established categories, CD45RO⁺CD45RA⁺). D. Node 4(+) labeled on t-SNE plot, with IL-17A heatmap for reference. Box-and-whisker plot of Node 4(+) abundance across subject groups on the left. E. Nodes 11(+), 12(−) t-SNE plot, abundance plots, and IFNγ/TNFα/CD8α heatmaps.

Figure 2.. Mucosal scRNA-seq identifies IL17A⁺ T cells in UC and CyTOF Analysis Demonstrates Expansion of HLA-DR⁺CD38⁺ T Cell Subsets in IBD

A. scRNA-seq of UCa subjects from CyTOF cohort (n=5 samples) represented by t-SNE plot colored by cluster (left; total cells analyzed = 3,979) with cluster identity labeled according to differential gene expression (see Table S6). Data was subsetted on T cells, which were then re-clustered (right; total cells analyzed = 718) with generation of 9 clusters labeled “0” through “8” (see Table S7, Supplemental Methods); cluster 1, corresponding to IL17A⁺ MAIT cells or IL17A⁺ CD8αα intraepithelial lymphocytes (IEL), is circled. B. Violin plots of selected transcripts, with expression profile of cluster 1 outlined. KLRB1 = CD161; ITGAE = CD103; GNLY = granulysin. All violin plots generated using standard Seurat v3.1 implementation; y-axis represents normalized and log-transformed expression data (log(scaled transcript counts +1)) C. Node 4(−) (from Fig 1C) abundance plot, t-SNE, and HLA-DR/CD38/CXCR3 heatmaps. D. Gating strategy defining HLA-DR⁺CD38⁺ T cells (left) with labeled t-SNE cluster plot (right) from dedicated clustering analysis. E. CyTOF marker heatmap, cluster dendrogram, cluster abundance and identity for HLA-DR⁺CD38⁺ T cell analysis with labeling strategy as per Fig 1C. F. Node 11(+) (from Fig 2E) abundance plot, t-SNE, and IL-1β heatmap.

Figure 3.. T Regulatory Cell (Treg) Analysis Demonstrates Expansion of Pro-Inflammatory Memory Treg Subsets in IBD

A. Gating strategy defining Tregs cells (left) with labeled t-SNE cluster plot (right) from dedicated clustering analysis. B. CyTOF marker heatmap, cluster dendrogram, cluster abundance and identity for Treg analysis with labeling strategy as per Fig 1C. C. Node 5(−) and Node 1(+) (from Fig 3B) abundance plots, t-SNE, and selected Treg marker heatmaps for reference. D. Clusters 7 and 8 (from Node 1(+) in Fig 3B) abundance plots, t-SNE, and TNFα/IFNγ/IL-17A marker heatmaps. E. Cluster 2 (from Fig 3B) abundance plot, t-SNE, and IL-1β marker heatmaps.

Figure 4.. B Cell Analysis Highlights Unique Naïve B Cell and Plasmablast Populations in IBD

A. Gating strategy defining B cells (left) with labeled t-SNE cluster plot (right) from dedicated clustering analysis. B. CyTOF marker heatmap, cluster dendrogram, cluster abundance and identity (color-coded by subset) organized as per Fig 1C. C. Node 8(+) (from Fig 4B) abundance plots, t-SNE, and IL-1β/TNFα/CCR7 marker heatmaps. D. Cluster 18 (from Node 10(−) in Fig 4B) abundance plots, t-SNE, and selected marker heatmaps.

Figure 5.. Innate Immune Cell Analysis Reveals Granulocyte and Dendritic Cell Differences in UC and CD

A. Gating strategy defining innate immune cells (left) with labeled t-SNE cluster plot (right) from dedicated clustering analysis. B. CyTOF marker heatmap, cluster dendrogram, cluster abundance and identity (color-coded by subset) organized as per Fig 1C. C. Node 9(−) (from Fig 5B) abundance plots, t-SNE, and CD38/CXCR3 marker heatmaps. D. Nodes 16(+) and 4(+) (from Fig 5B) abundance plots (combined), t-SNE, and selected marker heatmaps.

Figure 6.. CyTOF Demonstrates Differential Innate Lymphoid Cell and IL-1β-Related Macrophage/Monocyte Signatures in UC vs CD

A. Nodes 6(−) and 19(+) (from Fig 5B) abundance plots, t-SNE, and selected marker heatmaps. B. Cluster 30 (from Fig 5B) abundance plot, t-SNE, and CCR6 marker heatmap. C. Node 4(−) (from Fig 5B) abundance plot, t-SNE, and CD14 marker heatmap. D. Clusters 3 and 4 (from Fig 5B) abundance plot (combined), t-SNE, and IL-1β marker heatmap. E. Box-and-whisker plot of IL1B+CD14+ cells counted in ISH images (4 images per subject) with representative image.

Figure 7.. Signatures of Immune Dysregulation in IBD

Random forest (RF)-generated models of UCa:CDa discrimination in mucosa (A) and periphery (B). Receiver operator characteristic (ROC) curves (top panels) with models using top 3, top 6, and full model of input features shown. Area under the curve (AUC) for each model shown with associated p-value. Probability plots with associated confusion matrices (middle panels) demonstrating model accuracy of the full model. Top 10 features (in descending order of importance), representing isometric log-ratio of depicted nodes, with relative abundance of node branches in bar graphs and colored based on preferential abundance in UCa vs CDa (bottom panels). “In.”=“innate”. C. Schematic of key findings in IBD mucosa and periphery: IL-17A expression by several immune populations in UCa>CDa mucosa (CD161⁺ DN EM T cells, HLA-DR⁺CD38⁺ T cells and Tregs), IL-1β expression in CDa>UCa mucosa (in DCs, pDCs, HLA-DR⁺CD38⁺ T cells), expansion of granulocytes in UCa>CDa and ILC1 and ILC3 in CDa>UCa mucosa; and in the periphery, expansion of IL-1β⁺ Mφ/mono, DCs, and pDCs in CDa>UCa and expansion of Group 1 ILCs in UCa>CDa.